EUVIMEDEUVIMED entdecken
Crossref

Agentic Refactoring: An Empirical Study of AI Coding Agents

Kosei Horikawa, Hao Li, Yutaro Kashiwa, Bram Adams, Hajimu Iida, Ahmed E. Hassan

ACM Transactions on Software Engineering and Methodology · 21.10.2026

DOI: 10.1145/3859242 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 21.10.2026. Verfasst von Kosei Horikawa und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 75 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agentic coding tools, such as OpenAI Codex, Claude Code, and Cursor, are changing how software is developed. These AI-powered systems function as autonomous teammates capable of planning and executing complex development tasks. Agents have become active participants in refactoring, a key practice for improving internal code quality without altering observable behavior. Despite their increasing adoption, there is little empirical understanding of how agentic refactoring is used in practice, how it compares to human-driven refactoring, and what impact it has on code quality. To address this empirical gap, we present a large-scale study of AI agent-generated refactorings in real-world open-source Java projects, analyzing 51,412 refactoring instances across 12,256 pull requests and 14,998 commits based on the AIDev dataset. Our empirical analysis shows that refactoring is a common and intentional activity in this development paradigm, with agents explicitly targeting refactoring in 26.1% of commits. The subsequent analyses of refactoring types, purposes, and code quality focus on the 3,907 commits (32,611 instances) with explicit refactoring intent. Analysis of refactoring types reveals that high-level refactorings form the largest category overall. However, agentic refactoring contains a slightly larger share of lowlevel, consistency-oriented edits than human refactoring (27.6% vs. 24.4%), and its two most frequent operations are Rename Variable (7.6%) and Change Variable Type (6.8%). Additionally, the stated motivations behind agentic refactoring focus overwhelmingly on internal quality concerns (with 52.5% in maintainability and 28.1% in readability), although the measured metric improvements from these frequently occurring low-level refactorings remain limited. Furthermore, quantitative evaluation of code quality metrics shows that agentic refactoring yields small but statistically significant improvements in structural metrics, particularly for medium-level changes, reducing class size and complexity.

Zitieren

APA

Horikawa, K., Li, H., Kashiwa, Y., Adams, B., Iida, H., & Hassan, A. E. (2026). Agentic Refactoring: An Empirical Study of AI Coding Agents. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3859242

Vancouver

Horikawa K, Li H, Kashiwa Y, Adams B, Iida H, Hassan AE. Agentic Refactoring: An Empirical Study of AI Coding Agents. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3859242

BibTeX
@article{Horikawa2026,
  author = {Horikawa, Kosei and Li, Hao and Kashiwa, Yutaro and Adams, Bram and Iida, Hajimu and Hassan, Ahmed E.},
  title = {Agentic Refactoring: An Empirical Study of AI Coding Agents},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  doi = {10.1145/3859242}
}
Kostenlos starten →